Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations present, the description carries the full burden, and it does disclose the asynchronous contract (returns a request id, poll a sibling after about 3 minutes) plus a graceful-degradation path when documents are unreadable. It does not mention authentication, quota, or cost, so it falls short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first clause, and every sentence carries actionable content (inputs, formatting, polling, fallback). The middle sentences are dense and slightly run-on, but nothing is pure filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter, no-output-schema tool this covers the essentials: what is compared, how to supply documents, how results are retrieved asynchronously, and what to do when inputs cannot be read. The polling return value is explained in place of a missing output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 57%, and the description compensates meaningfully: it tells the agent lease_text must include amendments, that page-break markers preserve citation accuracy, and that lease_url/statement_url accept HTTPS PDF links. It leaves contact_email and property_name to the schema, which documents them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (checks/audits) and resource (CAM/operating expense reconciliation against the lease) and enumerates exactly what is compared: pro-rata share, caps, admin fees, excluded costs, gross-up, totals, late delivery. An agent can distinguish this from the sibling get_audit_result, which it also references by name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit input instructions (pass the full lease with amendments and the full reconciliation, mark page breaks as '--- page N ---', URLs also work), a sequencing rule (call get_audit_result after ~3 minutes), and a fallback path (tell the user to forward files to audit@tenantback.com if they cannot be read). This is close to a complete invocation playbook.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.